How to Use the FDA (openFDA) MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK setup handle rate limits when querying FDA (openFDA) endpoints?

Yes, you monitor your current API allowance by calling getusage directly within your agent loops. The SDK allows you to write custom retry logic or set cacheToolsList to true to avoid redundant schema lookups and protect your rate limits.

Q: How does the FDA (openFDA) toolset verify national drug codes within the OpenAI Agents SDK?

The agent invokes searchndc to match packaging codes against the official directory. This tool returns structured drug metadata, which the OpenAI Agents SDK validates against your agent's defined output schemas before passing the data to downstream clinical systems.

Q: What tools are available for monitoring medical hardware?

You query searchdeviceclassification to identify regulatory classes and searchdeviceenforcement to track hardware recalls. These tools let your agent evaluate the regulatory status of clinical equipment on the fly.

Build production-ready agents that query FDA clinical databases with built-in safety guardrails using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FDA (openFDA) MCP to OpenAI Agents SDK

Create your Vinkius account to connect FDA (openFDA) to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup FDA (openFDA) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safety-first drug recall tracking with OpenAI Agents SDK

This MCP Server exposes `search_drug_enforcement` to let your agent inspect active pharmaceutical recalls before executing clinical workflows. The OpenAI Agents SDK runs these queries within strict execution guardrails, preventing your system from taking actions based on outdated or retracted medication data. You configure validation rules directly in your Python code to verify the returned recall reasons. If an agent tries to recommend a flagged lot, the SDK blocks the handoff and triggers an immediate safety override.

Real-time drug shortage monitoring

Your agent uses `get_drug_shortages` to query the live FDA database for active and resolved supply disruptions. Instead of relying on static spreadsheets that go stale in hours, your production system pulls current market availability on demand. This direct integration lets your agent automatically calculate alternative medication options when a primary drug is out of stock. The agent checks the national registry via `search_ndc` to swap codes and keep your prescribing pipeline moving without manual intervention.

Automated adverse event analysis

The MCP Server exposes `search_drug_adverse_events` and `search_device_adverse_events` to feed post-market safety signals straight to your analytical agents. Your agent parses these reports to detect emerging safety trends or unexpected side effects across millions of clinical records. By using the SDK's native tracing dashboard, you can audit exactly how your agent filters these raw, unverified reports. This prevents the system from triggering false alerts over minor, non-causal events while ensuring critical safety signals are flagged for human review.

Setup guide

Set up FDA (openFDA) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all FDA (openFDA) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives FDA (openFDA) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate FDA (openFDA) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="FDA (openFDA) Agent",
            instructions="You have access to FDA (openFDA) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by FDA (openFDA). All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect FDA (openFDA) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about FDA (openFDA) MCP in OpenAI Agents SDK

Initialize MCPServerStreamableHttp with your Vinkius endpoint URL and pass it to your agent constructor. The OpenAI Agents SDK automatically discovers the 12 tools, including `search_drug_labels`, without manual schema definitions.

Yes, you monitor your current API allowance by calling `get_usage` directly within your agent loops. The SDK allows you to write custom retry logic or set cacheToolsList to true to avoid redundant schema lookups and protect your rate limits.

The agent invokes `search_ndc` to match packaging codes against the official directory. This tool returns structured drug metadata, which the OpenAI Agents SDK validates against your agent's defined output schemas before passing the data to downstream clinical systems.

You query `search_device_classification` to identify regulatory classes and `search_device_enforcement` to track hardware recalls. These tools let your agent evaluate the regulatory status of clinical equipment on the fly.

This MCP Server only queries public FDA (openFDA) data—like drug labels and food recalls—meaning no patient-identifying information or private medical records are ever processed or transmitted. Vinkius runs the server in an isolated sandbox, ensuring your API requests remain private while preventing external code execution.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript